Radar false alarm plots elimination based on multi-feature extraction and classification

doi:10.19682/j.cnki.1005-8885.2024.2008

中国邮电高校学报(英文) ›› 2024, Vol. 31 ›› Issue (1): 83-92.doi: 10.19682/j.cnki.1005-8885.2024.2008

• Others • 上一篇

Radar false alarm plots elimination based on multi-feature extraction and classification

Cheng Yi, Zhao Yan, Yin Peiwen

1. School of Control Science and Engineering, Tiangong University, Tianjin 300387, China 2. Tianjin Key Laboratory of Intelligent Control of Electrical Equipment,Tianjin 300387, China

收稿日期:2022-02-24 修回日期:2024-01-02 接受日期:2024-02-22 出版日期:2024-02-29 发布日期:2024-02-29
通讯作者: Corresponding author: Cheng Yi, E-mail: chengyi@tiangong.edu.cn E-mail:chengyi@tiangong.edu.cn

Radar false alarm plots elimination based on multi-feature extraction and classification

Cheng Yi, Zhao Yan, Yin Peiwen

1. School of Control Science and Engineering, Tiangong University, Tianjin 300387, China 2. Tianjin Key Laboratory of Intelligent Control of Electrical Equipment,Tianjin 300387, China

Received:2022-02-24 Revised:2024-01-02 Accepted:2024-02-22 Online:2024-02-29 Published:2024-02-29
Contact: Corresponding author: Cheng Yi, E-mail: chengyi@tiangong.edu.cn E-mail:chengyi@tiangong.edu.cn

摘要/Abstract

摘要： Caused by the environment clutter, the radar false alarm plots are unavoidable. Suppressing false alarm points has always been a key issue in Radar plots procession. In this paper, a radar false alarm plots elimination method based on multi-feature extraction and classification is proposed to effectively eliminate false alarm plots. Firstly, the density based spatial clustering of applications with noise (DBSCAN) algorithm is used to cluster the radar echo data processed by constant false-alarm rate (CFAR). The multi-features including the scale features, time domain features and transform domain features are extracted. Secondly, a feature evaluation method combining pearson correlation coefficient (PCC) and entropy weight method (EWM) is proposed to evaluate interrelation among features, effective feature combination sets are selected as inputs of the classifier. Finally, False alarm plots classified as clutters are eliminated. The experimental results show that proposed method can eliminate about 90% false alarm plots with less target loss rate.

关键词: radar plots elimination, density based spatial clustering of applications with noise, multi-feature extraction, classifier

Abstract: Caused by the environment clutter, the radar false alarm plots are unavoidable. Suppressing false alarm points has always been a key issue in Radar plots procession. In this paper, a radar false alarm plots elimination method based on multi-feature extraction and classification is proposed to effectively eliminate false alarm plots. Firstly, the density based spatial clustering of applications with noise (DBSCAN) algorithm is used to cluster the radar echo data processed by constant false-alarm rate (CFAR). The multi-features including the scale features, time domain features and transform domain features are extracted. Secondly, a feature evaluation method combining pearson correlation coefficient (PCC) and entropy weight method (EWM) is proposed to evaluate interrelation among features, effective feature combination sets are selected as inputs of the classifier. Finally, False alarm plots classified as clutters are eliminated. The experimental results show that proposed method can eliminate about 90% false alarm plots with less target loss rate.

Key words: radar plots elimination, density based spatial clustering of applications with noise, multi-feature extraction, classifier

Cheng Yi, Zhao Yan, Yin Peiwen. Radar false alarm plots elimination based on multi-feature extraction and classification[J]. The Journal of China Universities of Posts and Telecommunications, 2024, 31(1): 83-92.

参考文献

References

[1] QI Y M, LIU Z C, YU C Z, et al. Research into the classification techniques of radar plots based on CNN. Shipboard Electronic Countermeasure, 2021, 44(3): 53 - 57 (in Chinese).

[2] CHANG Y, CAI X Y, LUO L Q, et al. A radar clutter filtering method based on space-time correlation. Fire Control Radar Technology, 2020, 49(3): 47 - 50 (in Chinese).

[3] HU Q Y, XIE J W, LIU Z Q. False-targets discrimination method based on measurement fusion. Journal of Nanjing University of Posts and Telecommunications (Natural Science Edition), 2017, 37(3): 88 - 92 (in Chinese).

[4] GUAN L H. Research on plots filtering technology of ground-based surveillance radar. Electronic Technology and Software Engineering, 2018, 40(17): 119 - 121 (in Chinese).

[5] LI H W, WANG Y. Research on clutter dots filtering techniques based on inter-frame data processing. Radio Engineering, 2019, 49(2): 145 - 149 (in Chinese).

[6] ZHENG H, WANG W, SA C L. Clutter plot filtering technology based on error detecting. Command Information System and Technology, 2019, 10(4): 72 - 76 (in Chinese).

[7] FU Q, LI R Y. A residual clutter plots filtering method for low altitude blind compensation radar. Heilongjiang Science and Technology Information, 2017, 40(15): 104 (in Chinese).

[8] SHI J T, YANG Y H, SUN J, et al. A plots filtering method for radar targets based on clutter feature evaluation. Journal of Terahertz Science and Electronic Information Technology, 2019, 17(6): 988 - 993 (in Chinese).

[9] XING Y J, CHEN Y, ZHU H, et al. Filtering ground-clutter-false-alarms using supported vector machine. Modern Radar, 2016, 38(8): 34 - 38 (in Chinese).

[10] LI Y. Characteristic recognition method of ship radiated noise based on Bayesian. Ship Science and Technology, 2023, 45(7): 70 - 73 (in Chinese).

[11] XUE S Y, LI P, ZHOU Y. Voltage sag source identification based on feature selection and Bayesian discrimination. Electric Engineering, 2023(17): 58 - 62 (in Chinese).

[12] LI X Q, YANG Z, REN J. Improved naive Bayes algorithm based on dual feature selection of mutual information and hierarchical clustering. Measurement and Control Technology, 2022, 41(2): 36 - 40 (in Chinese).

[13] LI S, WANG S L. Radar plots classification method based on BP neural network. Modern Radar, 2018, 40(12): 52 - 56 (in Chinese).

[14] YAN M D, YANG R N, WANG X, et al. Air combat target grouping based on improved CBSCAN algorithm. Journal of National University of Defense Technology, 2021, 43(4): 108 - 117 (in Chinese).

[15] YAN W L, FANG Z H, RUAN X C, et al. The radar plots centroid technology and data analysis. Signal Processing, 2001(2): 130 - 138 (in Chinese).

[16] JI J. Intelligent radar point target trace feature extraction method. Information Technology, 2013, 37(6): 83 - 87 (in Chinese).

[17] DAN B, GAO S, JI Z H. Sea surface ship target recognition technology based on multiple features and multiple classifiers. Ship Electronic Engineering, 2020, 40(8): 49 - 53 (in Chinese).

[18] MOU X Q, CHEN X L, SU N Y, et al. Motion classification for radar moving target via STFT and convolution neural network. The Journal of Engineering, 2019, 2019(19): 6287 - 6290.

[19] BHATIA J, DAYAL A, JHA A, et al. Classification of targets using statistical features from range FFT of mmwave FMCW radars. Electronics, 2021, 10(16): 115 - 119.

[20] DONG Y, LU Y L. Research on gene regulatory network based on correlation analysis and principal component analysis. Journal of Jilin Institute of Chemical Technology, 2021, 38(9): 112 - 116 (in Chinese).

[21] WANG F Q, XU T X, YAN T L. Research on flight action recognition based on CART decision tree algorithm. Ship Electronic Engineering, 2021, 41(8): 51 - 53 (in Chinese).

Radar false alarm plots elimination based on multi-feature extraction and classification

Radar false alarm plots elimination based on multi-feature extraction and classification

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价